Taxonomic framework for neural network-based anomaly detection in bridge monitoring

Accurate differentiation between damage-related anomalies and data errors is a critical challenge in bridge monitoring. This paper presents a data-driven framework for anomaly detection and classification, addressing the question: How can anomalies be classified in multi-sensor bridge monitoring to distinguish structural changes from noise? The framework combines an adapted anomaly taxonomy with a deep neural network trained on synthetic data. It is validated using long-term monitoring data from a railway bridge, incorporating strain gauges, accelerometers, and an inclinometer. In offline training, the model achieves high precision, recall, and F1-scores, effectively detecting anomaly classes across sensor types. For online prediction, it provides anomaly type percentages and visualizations over daily, weekly, and annual timeframes, distinguishing frequent noise-related anomalies from rare anomalies signaling structural changes. Requiring one month of training data, the framework delivers a scalable solution for bridge monitoring and lays the groundwork for future self-learning anomaly detection in infrastructure management. • A neural network based framework is developed to automate anomaly detection and classification in bridge monitoring data. • An anomaly taxonomy is established to prepare monitoring data for training supervised models for the detection and classification of anomalies in bridges. • Case study results demonstrate high accuracy and precision in detecting and classifying anomalies across a range of sensor types, loading phases, and anomaly categories. • Application of the framework to the long-term monitoring of a bridge offers valuable insights into structural behaviour and sensor performance.